Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2746 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.6129. Min Act: -0.1700
Data Index: 7261405 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.5191. Min Act: -0.1700
Data Index: 7076889 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.4879. Min Act: -0.1700
Data Index: 987216 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.4566. Min Act: -0.1700
Data Index: 7076891 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.4566. Min Act: -0.1700
Data Index: 4503032 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.4254. Min Act: -0.1700
Data Index: 356569 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.4254. Min Act: -0.1700
Data Index: 1797188 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3941. Min Act: -0.1700
Data Index: 6462794 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3941. Min Act: -0.1700
Data Index: 3234141 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3316. Min Act: -0.1700
Data Index: 4725562 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3629. Min Act: -0.1700
Data Index: 4204893 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3316. Min Act: -0.1700
Data Index: 7395980 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3316. Min Act: -0.1700
Data Index: 5661922 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3316. Min Act: -0.1700
Data Index: 2230574 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3004. Min Act: -0.1700
Data Index: 6445287 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3004. Min Act: -0.1700
Data Index: 5981475 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3004. Min Act: -0.1700
Data Index: 6780935 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3004. Min Act: -0.1700
Data Index: 4878274 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3004. Min Act: -0.1700
Data Index: 5444653 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6129. Min Range: -4.6129
Max Act: 4.3004. Min Act: -0.1699
Data Index: 5649920 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19